Ling7800/CSCI 7000: Computational Lexical Semantics

Fall 2014

Instructors:
Martha Palmer and occasionally James Pustejovsky
Time and Location: Tue/Thur, 11:00 - 12:15, Ketchum 301, and some Fridays, 10:30-12, Hellems 285
Assessment: Five homeworks, one Paper presentation, and a term project.
Office Hours: Martha Palmer, Hellems 295, Tuesday 5-6pm, Thursday 1-2pm

Textbooks:
Semantic Role Labeling (eBook), Martha Palmer, Daniel Gildea, Nianwen Xue,
Synthesis Lectures on Human Language Technologies ,
ed., Graeme Hirst, Morgan & Claypool, 2010. ISBN: 9781598298321
available on line on campus through Chinook

Representation and Inference for Natural Language. A First Course in Computational Semantics.
Patrick Blackburn and Johan Bos, 2005, CSLI Publications. ISBN: 1-57586-496-7
available from the CU bookstore

Theme

Lexical semantics is becoming an increasingly important part of Natural Language Processing (NLP), as the field is beginning to address semantics at a large scale. This introductory lecture course will cover key issues in computational lexical semantics. We will start with an introduction to theoretical models of lexical semantics and events, considering both their adequacy as linguistic models and their place in NLP. We will focus particularly on computational lexical resources such as PropBank, VerbNet and the Generative Lexicon, and examine their strengths and limitations with respect to NLP applications. We will introduce apporoaches to developing automatic classifiers that are intended to make use of these resources and to offer richer representations of sentences in context. These techniques can be fully supervised (requiring hand-labeled training data), semi-supervised, or unsupervised (learning lexical information from unlabeled text). Several lectures will be shared with a parallel CS course on Computational Semantics being run by Professor James Pustejovsky at Brandeis University, who will avail us of his expertise in semantics, especially with respect to the Generative Lexicon and Event Representations.

Suggested Schedule and Readings

Introduction and Module 1: the Lexical Semantics of Verbs - Chap 1

Module 2: Available Computational Lexicons - Chap 2

Module 3: Semantic representations

Module 4: Representations of Events

Final Exam - Student Project Presentations, Tuesday, Dec 16, 4:00-7:30pm MUEN D 430, ICS Large conference room

Machine Learning Background

  • Tom M. Mitchell, 2006, Machine Learning Department technical report CMU-ML-06-108, Carnegie Mellon University, The Discipline of Machine Learning
  • Machine Learning Resources/Links
  • Dan Klein's Machine Learning for Natural Language Processing: New Developments and Challenges (slides and video)
    Michael Collins tutorial on NLP
    Introduction to Machine Learning, S V N Vishwanathan
    Weka, a collection of machine learning algorithms for data mining tasks.
    Orange, Open source data visualization and analysis for novice and experts. Data mining through visual programming or Python scripting.
    Videos of Andrew Ng's Stanford ML course
    Noah Smith's course titled Language and Statistics, at CMU